Pages: [1] 2 3 4 5 6 7 :: one page |
|
Author |
Thread Statistics | Show CCP posts - 24 post(s) |
|
CCP Dolan
C C P C C P Alliance
748
|
Posted - 2013.12.03 15:29:00 -
[1] - Quote
Check out some math and numbers that make me feel dumb, and make the server feel great with CCP Prism X's new Dev Blog. CCP Dolan | Community Representative
Twitter: @CCPDolan
Gooby pls |
|
Steve Ronuken
Fuzzwork Enterprises Vote Steve Ronuken for CSM
2115
|
Posted - 2013.12.03 15:30:00 -
[2] - Quote
First! (now to read) Steve Ronuken for CSM 9! http://www.fuzzwork.co.uk/ Twitter: @fuzzysteve on Twitter |
|
CCP Prism X
C C P C C P Alliance
1386
|
Posted - 2013.12.03 15:36:00 -
[3] - Quote
I hear this guy listens to really stupid music (NSFW) which is probably indicative of his cognitive capacity. Probably not worth reading this! @CCP_PrismX EVE Database Developer and Expert Ranter Member of a Different Team, every day. |
|
|
CCP Explorer
C C P C C P Alliance
1872
|
Posted - 2013.12.03 15:40:00 -
[4] - Quote
I'm more scared and scarred of his pictures. Not the pictures in this devblog though, they are safe. Erlendur S. Thorsteinsson | Development Director | EVE Online // CCP Games | @erlendur |
|
Weaselior
GoonWaffe Goonswarm Federation
5615
|
Posted - 2013.12.03 15:40:00 -
[5] - Quote
I have a concern. As you point out, this system means that ajacent systems tend to share the same physical hardware.
Doesn't that massively increase the chances of spillover tidi in nullsec battles: i.e. our staging system is overloaded so every system next to it is overloaded, massively increasing the pain in the ass to leave? Or the system the fight is in is massively overloaded, causing all systems around it to be massively overloaded as well making it a giant pain in the ass to get there? "I can hire one-half of the working class to kill the other half." |
Fix Lag
Federal Navy Academy Gallente Federation
587
|
Posted - 2013.12.03 15:48:00 -
[6] - Quote
The stuff outlined in the devblog certainly is some cool shit. But as Weaselior said, sticking adjacent systems all on the same node penalizes subcapitals traveling between gates when massive fights are going on. |
Oh Takashawa
Body Count Inc. Pandemic Legion
4
|
Posted - 2013.12.03 15:48:00 -
[7] - Quote
Weaselior wrote:I have a concern. As you point out, this system means that ajacent systems tend to share the same physical hardware.
Doesn't that massively increase the chances of spillover tidi in nullsec battles: i.e. our staging system is overloaded so every system next to it is overloaded, massively increasing the pain in the ass to leave? Or the system the fight is in is massively overloaded, causing all systems around it to be massively overloaded as well making it a giant pain in the ass to get there? Let's take it one step further - let's say I'm an alliance with huge numbers that doesn't want to commit to fighting in some situation. I can simply go *nearby* under this model, causing massive tidi and suffering for my opponents, without ever actually engaging in a figth. Or I can bridge huge piles of reinforcements somewhere nearby, slowing down the constellation enough to buy me much more time to form, reducing or eliminating the target's ability to extract and giving me more leeway to be slow at forming.
And all this, impacting thousands of players in EVE's biggest wars, to avoid inconveniencing a few ratters on the other side of EVE every now and then. Seriously? |
|
CCP Prism X
C C P C C P Alliance
1387
|
Posted - 2013.12.03 15:50:00 -
[8] - Quote
Weaselior wrote:I have a concern. As you point out, this system means that ajacent systems tend to share the same physical hardware.
Doesn't that massively increase the chances of spillover tidi in nullsec battles: i.e. our staging system is overloaded so every system next to it is overloaded, massively increasing the pain in the ass to leave? Or the system the fight is in is massively overloaded, causing all systems around it to be massively overloaded as well making it a giant pain in the ass to get there?
If your fighting system is reinforced that shouldn't be an issue. This is also no more of an issue than it used to be, and now the TiDi you create in your staging systems will at least not be affecting players on the other side of the universe who have nothing to do with your pew pew.
And of course more nullsec nodes mean smaller pockets grouped together. @CCP_PrismX EVE Database Developer and Expert Ranter Member of a Different Team, every day. |
|
Oh Takashawa
Body Count Inc. Pandemic Legion
4
|
Posted - 2013.12.03 15:53:00 -
[9] - Quote
CCP Prism X wrote:Weaselior wrote:I have a concern. As you point out, this system means that ajacent systems tend to share the same physical hardware.
Doesn't that massively increase the chances of spillover tidi in nullsec battles: i.e. our staging system is overloaded so every system next to it is overloaded, massively increasing the pain in the ass to leave? Or the system the fight is in is massively overloaded, causing all systems around it to be massively overloaded as well making it a giant pain in the ass to get there? If your fighting system is reinforced that shouldn't be an issue. This is also no more of an issue than it used to be, and now the TiDi you create in your staging systems will at least not be affecting players on the other side of the universe who have nothing to do with your pew pew. And of course more nullsec nodes mean smaller pockets grouped together. Ok, but that also means that by staging near my enemies and having more numbers than them, I can basically permanently annoy my enemies purely by undocking, or just having lots of people around. Or I can lag out their staging, keeping them from logging in reinforcements, purely by having dudes of my own jumping out. There's all kinds of **** I can do, while on the other side of the universe, where there's no war, whole nodes will be dedicated to supporting a dozen systems populated by 20 dudes ratting. |
Muscaat
EVE Markets
51
|
Posted - 2013.12.03 15:53:00 -
[10] - Quote
Love these behind-the-scenes techy dev blogs. Thanks Prism X! |
|
Fix Lag
Federal Navy Academy Gallente Federation
587
|
Posted - 2013.12.03 15:54:00 -
[11] - Quote
CCP Prism X wrote:[quote=Weaselior]and now the TiDi you create in your staging systems will at least not be affecting players on the other side of the universe who have nothing to do with your pew pew.
But I want horrible, mindless mission runners slaving away in some corner of highsec to suffer as I do through massive fleet fight lag: sharing the experience of nullsec warfare one extra slow tick at a time. |
Forlorn Wongraven
Habitual Euthanasia Pandemic Legion
101
|
Posted - 2013.12.03 15:54:00 -
[12] - Quote
CCP Prism X wrote:If your fighting system is reinforced that shouldn't be an issue. This is also no more of an issue than it used to be, and now the TiDi you create in your staging systems will at least not be affecting players on the other side of the universe who have nothing to do with your pew pew. Pretty much all recent important battles actually happened as escalations upon escalations. So those systems are never reinforced. These seems a little bit stupid, although the first idea is actually pretty good. Shadoo > whoever was the first nyx on grid Shadoo > THANK GOD YOU ARE A SMART MAN and fitted the best tank in PL Shadoo > (ie. cyno) |
Weaselior
GoonWaffe Goonswarm Federation
5616
|
Posted - 2013.12.03 15:55:00 -
[13] - Quote
CCP Prism X wrote:If your fighting system is reinforced that shouldn't be an issue. This is also no more of an issue than it used to be, and now the TiDi you create in your staging systems will at least not be affecting players on the other side of the universe who have nothing to do with your pew pew. And of course more nullsec nodes mean smaller pockets grouped together. The bolded part concerns me. It makes a certain amount of sense to avoid inconveniencing the three people in some system in Solidude for reasons they don't understand, sure. However it also makes a great deal of sense when you have a cluster of systems expected to be used heavily to offload the issues caused in those systems to unused systems in buttfuck nowhere as a sort of heat sink - it seems to me that it is better to be inconveniencing three ratters in Solitude because of 1000 people in nullsec than doubly inconveniencing those 1000 people in nullsec. "I can hire one-half of the working class to kill the other half." |
GeeShizzle MacCloud
390
|
Posted - 2013.12.03 15:56:00 -
[14] - Quote
exceptional work there Prism! hopefully tidi will be spread in a more understandable manner and the cluster pre-mapper will act in a more elegant way!
<3 |
Kimimaro Yoga
The Praxis Initiative Gentlemen's Agreement
28
|
Posted - 2013.12.03 15:56:00 -
[15] - Quote
The many systems with massive lag in one area problem is semi-solveable by simply buying more regular not-crazy-expensive servers, and thus reducing the total # of systems per server. While I hate crawling through tidi to get to a fight, well on the one hand it is fairer if everyone traveling to a fight is getting there at the same speed. Minimizing the chances of one fleet traveling without tidi while their opponents are crushed by it. And on the other hand... taking gates is for poor people anyways. Get more titans. :P
Unrelated question for Prism X: Why is it that the Empire nodes have so much more peak traffic than the nullsec systems? Is this to compensate for the occasional extreme swings in nullsec load (huge unexpected fights) that have no highsec equivalent, or something else? http://imageshack.us/photo/my-images/24/0dbl.jpg -á-á-áJoin The War Today! |
|
CCP Prism X
C C P C C P Alliance
1387
|
Posted - 2013.12.03 15:57:00 -
[16] - Quote
There seems to be an image missing there right now and some problem with our CDN. Hopefully that will get resolved soon, but it's why there's no "visualization" for the splitting process. Just a table of stats. @CCP_PrismX EVE Database Developer and Expert Ranter Member of a Different Team, every day. |
|
Oh Takashawa
Body Count Inc. Pandemic Legion
6
|
Posted - 2013.12.03 15:58:00 -
[17] - Quote
Kimimaro Yoga wrote:Unrelated question for Prism X: Why is it that the Empire nodes have so much more peak traffic than the nullsec systems? Is this to compensate for the occasional extreme swings in nullsec load (huge unexpected fights) that have no highsec equivalent, or something else? I'm gonna guess higher average population, higher traffic, higher market activity - more of everything, on average, than most nullsec systems. |
Aquila Sagitta
Blue-Fire
110
|
Posted - 2013.12.03 16:01:00 -
[18] - Quote
How is this being applied to wh systems? Blue-Fire Best Fire |
GeeShizzle MacCloud
390
|
Posted - 2013.12.03 16:03:00 -
[19] - Quote
Weaselior wrote:CCP Prism X wrote:If your fighting system is reinforced that shouldn't be an issue. This is also no more of an issue than it used to be, and now the TiDi you create in your staging systems will at least not be affecting players on the other side of the universe who have nothing to do with your pew pew. And of course more nullsec nodes mean smaller pockets grouped together. The bolded part concerns me. It makes a certain amount of sense to avoid inconveniencing the three people in some system in Solidude for reasons they don't understand, sure. However it also makes a great deal of sense when you have a cluster of systems expected to be used heavily to offload the issues caused in those systems to unused systems in buttfuck nowhere as a sort of heat sink - it seems to me that it is better to be inconveniencing three ratters in Solitude because of 1000 people in nullsec than doubly inconveniencing those 1000 people in nullsec. I don't mean to criticize the work you've done here - this all looks extremely impressive. I'm just concerned that it's assumptions on nullsec battles are not correct and may wind up creating more inconvenience overall in certain situations.
afaik from the dev blog it wont work exactly as you would say. if your staging close to a hostiles staging then upon downtime when the server runs a new premapping it may identify the staging systems as load hotspots and could well at the last splitting to discrete servers decide to split your staging and the hostiles staging to different servers.
if u plan on changing alliance / coalition staging once every day after downtime then i guess you could still grief in your original way.
Prism... the pre-loader to split the cluster load runs every downtime right? |
Koban Agalder
Future Corps Sleeper Social Club
27
|
Posted - 2013.12.03 16:05:00 -
[20] - Quote
So where WH ends in this big colorfull picture ?
We had experienced some TiDi recently :P Hopefully this last way of nullbears affecting WH will be solved! James Arget for CSM 8!-áhttp://csm.fcftw.org-á |
|
Berluth Luthian
Meltdown.
135
|
Posted - 2013.12.03 16:06:00 -
[21] - Quote
With the new warp speed changes, has the inter-node velocity of players increased on average? IOW, if we have interceptor wolf-packs loading grids at 2-3x the rate as before, would they be stressing the system in new ways?
1) How is the 'regionality' of wormhole space determined? I can't tell if it is on your chart?
2) Presumably with upcoming expansions we are getting 'new space'. Do you anticipate that this space will have similar proximity issues, or will it not necessarily be as well traveled or as relatively 'local' as current systems? Are you building your balance model to compensate for this new space when it comes? Let's say for example, we have to invest both time and resources in order to locate these new systems. Then let's say that in order to get to them you have to have a looong initial warp time (lightyears > hours) with a normal warp engine. I can conceive that this would be the kind of space, like wormholes, in which fights would escalate VERY quickly. Enemy fleets would have to be ready to escalate immediately after their long warping 'anchor' ship arrives in system and before it is detected. |
Borachon
GoonWaffe Goonswarm Federation
13
|
Posted - 2013.12.03 16:07:00 -
[22] - Quote
"Hey, look, we reinvented load balancing by recursive bi-section!": http://www.netlib.org/utk/lsi/pcwLSI/text/node253.html
Seriously, though, load balancing/graph coloring/graph partitioning has been researched by the high-performance computing community for literally decades, as well as in the data center and cloud computing environment more recently. As a result, there's a huge body of work, both in terms of publications and source code, that you could draw on here instead of having to rediscover the issues yourselves. As another starting point (outside of netlib, linked above, or google scholar), the Zoltan project out of Sandia National Labs has dealt with this issue head-on, and includes implementations of lots of different load balancing algorithms. It even includes a Python interface... |
Grarr Dexx
Snuff Box
299
|
Posted - 2013.12.03 16:07:00 -
[23] - Quote
Looks like a whole load of baloney! Us lowsec residents have been suffering from utterly ridiculous amounts of tidi, in sub-100 man fights or even moving thirty people ten gates. If you did do this rebalancing act, you sure seemed to have forgotten the systems between 0.5 and 0.0. |
Rob Crowley
State War Academy
258
|
Posted - 2013.12.03 16:08:00 -
[24] - Quote
I think I know why they had you rewrite the blog: All the pictures look like stuff my cat throws up. And only 1 out of 8 is reasonably pink! You better go ask Punkturis how it's done.
Other than that: nice blog, interesting sheet. |
|
CCP Prism X
C C P C C P Alliance
1388
|
Posted - 2013.12.03 16:10:00 -
[25] - Quote
Wormholes do not need to be split by proximity. There's no sense of locality or proximity in WH space so they just get a very dumb but efficient method applied to them.
However I reduced the number of nodes running WH space. We've added a few back, apparently I should look at adding more before the weekend.
Sorry
Edit: Yes this distribution is remade every startup. @CCP_PrismX EVE Database Developer and Expert Ranter Member of a Different Team, every day. |
|
Weaselior
GoonWaffe Goonswarm Federation
5623
|
Posted - 2013.12.03 16:10:00 -
[26] - Quote
GeeShizzle MacCloud wrote: afaik from the dev blog it wont work exactly as you would say. if your staging close to a hostiles staging then upon downtime when the server runs a new premapping it may identify the staging systems as load hotspots and could well at the last splitting to discrete servers decide to split your staging and the hostiles staging to different servers.
if u plan on changing alliance / coalition staging once every day after downtime then i guess you could still grief in your original way.
Prism... the pre-loader to split the cluster load runs every downtime right?
This may or may not work for larger-scale wars. It's actually much more important that the system intelligently infer from node reinforcement requests I think when it comes to nullsec battles, because that's a much better indication of where the people with the most information expect the most load - and from those points you can infer spillover load (ok, these three points are to be reinforced: it follows from there that the surrounding systems are likely to see heavy traffic as well).
It does not solve the escalation problem, where a battle that was not pre-planned causes its lag to be exponentially increased because the fight and all surrounding systems are on the same node as people try to get in. Yes, many people titan-bridge in or cyno in, but many people will also be taking the gates from nearby systems. Because surprise load in nullsec tends to be strongly correlated with surprise load for every adjacent system, it's not good for a node that expects to have a quiet day to have all of those systems. That ensures that when a suprise asakai breaks out, that only one or two nodes at most are stressed. Were the nodes in nullsec more randomly allocated, you'd tend to see the fight on one node and each surrounding system on a different node, spreading the load.
This is why the idea of clumping together nearby systems on the same node doesn't make sense to me. The choice being made here seems to be avoiding inexplicable lag (the three ratters in solitude going why the **** is my system lagged) by increasing actual lag. I don't really understand why that tradeoff is being made. "I can hire one-half of the working class to kill the other half." |
Efraya
Dissident Aggressors Mordus Angels
240
|
Posted - 2013.12.03 16:10:00 -
[27] - Quote
Interested and well thought out Devblog CCP PrismX.
WSpace; Best space. |
Kimimaro Yoga
The Praxis Initiative Gentlemen's Agreement
28
|
Posted - 2013.12.03 16:11:00 -
[28] - Quote
Speaking of reducing the number of systems per server... now that your node mapper is making tidy clusters, could you use it to reduce the tidi in systems around declared "need to reinforce" nodes?
What I'm thinking is a temporary bump up to the load fingerprint in say, all systems within three jumps of a system that's been requested to be reinforced. You know the neighboring systems will be heavily hit as well. So the reinforce request would automatically kick up the fingerprint of nearby systems, and the premapper would allocate to them more server power for that one day. Since the capacity would be drawn from basically the entirety of the rest of New Eden, you could quite effectively improve the gameplay in the systems surrounding a reinforced node without causing much trouble at all for anyone else. The worst case scenario would be that some slightly overloaded server would cause just a teeny bit of tidi during peak hours. http://imageshack.us/photo/my-images/24/0dbl.jpg -á-á-áJoin The War Today! |
Lipbite
Express Hauler
1536
|
Posted - 2013.12.03 16:11:00 -
[29] - Quote
First paragraph is very interesting to read, last phrase describes the rest ("you get frustrated"). |
R0ze
GK inc. Pandemic Legion
12
|
Posted - 2013.12.03 16:12:00 -
[30] - Quote
How long till CCP puts each solarsystem at least on one physical core?
I mean with systems like HP Moonshot / also Intel announcing Knights Landing you could literally do that in a single server rack (with 7800 cpu cores or so). |
|
|
|
|
Pages: [1] 2 3 4 5 6 7 :: one page |
First page | Previous page | Next page | Last page |